Dify deployment notes
Open-source LLM app platform for agents, workflows, and knowledge bases.
Deployment verdict
Dify is best read as an LLM application platform rather than a simple chatbot. Its value is strongest when a team wants a visible workflow layer for prompts, knowledge bases, agents, model routing, and app publishing. The tradeoff is operational complexity: once you move beyond a demo, credentials, datasets, plugin behavior, user permissions, and model cost control all need ownership.
Before installing
- Review the license: Apache-2.0.
- Check whether Docker is supported: yes.
- Check API key dependency: depends on model/provider.
- Confirm supported models: OpenAI, Claude, Gemini, Ollama, DeepSeek, Qwen.
Recommended deployment path
- Start with the official Docker Compose path in a disposable environment.
- Connect one model provider first; avoid enabling every provider at once.
- Create a small knowledge base with 20 to 50 known documents, then test answer quality against questions with known answers.
- Only after retrieval quality is acceptable should you add users, plugins, and external workflows.
Common evaluation traps
- A successful login page does not prove the RAG pipeline is useful.
- Plugin and tool permissions should be reviewed before connecting private systems.
- The real cost is often model calls plus maintenance, not the open-source license.
Acceptance test tasks
- Build one knowledge-base app from a controlled document set.
- Ask five factual questions, three synthesis questions, and two adversarial questions.
- Export or document the prompt, model, retrieval settings, and failure cases.
Setup commands
git clone https://github.com/langgenius/dify.gitcd dify/dockercp .env.example .envdocker compose up -d